Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5049 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.1038. Min Act: -0.1700
Data Index: 2577435 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.1038. Min Act: -0.1700
Data Index: 3367427 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.0726. Min Act: -0.1700
Data Index: 5650227 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.0413. Min Act: -0.1700
Data Index: 2857769 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.0413. Min Act: -0.1700
Data Index: 5630001 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.0101. Min Act: -0.1700
Data Index: 7586944 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.0413. Min Act: -0.1700
Data Index: 5363388 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.0413. Min Act: -0.1700
Data Index: 6495323 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.0413. Min Act: -0.1700
Data Index: 5839372 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1038. Min Range: -5.1038
Max Act: 5.0101. Min Act: -0.1700
Data Index: 5591237 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9788. Min Act: -0.1700
Data Index: 1715105 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9788. Min Act: -0.1700
Data Index: 7021517 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9788. Min Act: -0.1700
Data Index: 3036820 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9788. Min Act: -0.1700
Data Index: 6484096 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9476. Min Act: -0.1700
Data Index: 7147244 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9476. Min Act: -0.1700
Data Index: 65258 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9788. Min Act: -0.1700
Data Index: 4406061 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9476. Min Act: -0.1700
Data Index: 7668734 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9476. Min Act: -0.1700
Data Index: 8267254 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1038. Min Range: -5.1038
Max Act: 4.9163. Min Act: -0.1700
Data Index: 3295968 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19